Paper Contents
Abstract
Drones have been frequently used for aerial photography in recent years at significantly cheaper rates. However, the most modern drones are exceedingly error-prone and require precise manual control to take high-quality photos or films. We suggest using quadcopters equipped with object monitoring to power drones equipped with cameras, enabling the drone to perform automatic tracking and detection. We used cutting-edge detection and tracking algorithms to implement the visual part of this project. Our system was put into use on a variety of hardware platforms, including both desktop and GPU (NVIDIA GTX980) and embedded GPU (NVIDIA Tegra K1 and NVIDIA Tegra X1) and evaluated frame rate, power consumption and accuracy on several videos captured by the drone. Our system achieved real time performance at 71 frames per second (fps) for tracking and 1.6 fps for detection on NVIDIA TX1.
Copyright
Copyright © 2023 KarunaPedige Sugandika Sandamali. This is an open access article distributed under the Creative Commons Attribution License.
